Use the Aspire Dashboard Standalone
Stop setting up complex observability stacks for local dev. Learn how to run the Aspire Dashboard as a standalone, lightweight OTLP viewer for any language.
Posts
Practical articles about .NET, Azure, AI engineering, architecture, evaluation, observability, retrieval, and reliable delivery.
Chat vs. Streaming: Don't Keep Your Users Waiting
Series
Deep Dive: Microsoft Agent Framework
Part 3 of 19
When to use RunAsync vs. RunStreamingAsync in Microsoft Agent Framework, and why streaming improves chat UX while blocking calls still fit structured outputs and background work.
Zero to First Agent
Series
Deep Dive: Microsoft Agent Framework
Part 2 of 19
How to initialize the Microsoft Agent Framework, connect to Azure, OpenAI or local Ollama models and execute your first asynchronous agent run.
Microsoft Agent Framework: Introduction
Series
Deep Dive: Microsoft Agent Framework
Part 1 of 19
How Microsoft Agent Framework builds on Microsoft.Extensions.AI, when it supersedes Semantic Kernel for new .NET agent systems, and where MCP, context providers, and workflows fit.
Context Compression in .NET
Reduce token cost and latency in .NET by compressing RAG context with a cheap summarizer model or an IChatClient middleware pipeline.
Stop Guessing – Use Golden Datasets for Prompt Evals
Use a small golden dataset to catch prompt regressions, compare changes against a baseline, and validate model updates before users do.
Indirect Prompt Injection Is a Trust Boundary Problem
Indirect prompt injection is a trust-boundary failure; treat retrieved content as untrusted data, isolate it from instructions, and validate actions before execution.
Stop RAG Hallucinations with the Short-Circuit Pattern
How to reduce RAG hallucinations by short-circuiting generation when retrieval returns weak evidence, with a simple C# threshold check.
RAG Is a Data Problem Before It’s a Prompt Problem
Why stale documents, weak chunking, and thin metadata usually break RAG before prompt tuning does.
Debugging LLM Timeouts in .NET
A repeatable local setup for timeout triage in .NET LLM workloads using Aspire, OpenTelemetry, and Ollama.